Abstract
This chapter provides an overview of two different clinical studies that apply machine learning techniques that create computational models capable of identifying abnormal network connections in the structural brain connectomes of patients with temporal lobe epilepsy (TLE). In particular, using only the structural connectome we introduce two new computational approaches aimed at predicting: (1) the surgical treatment outcome of patients with TLE, and (2) the naming impairment performance of patients with TLE. In both studies, prediction frameworks are trained to identify abnormal network connection patterns (ie, biomarkers) by applying supervised learning techniques to brain network features based on edge or node graph measures derived exclusively from the structural connectome. Furthermore, the performance of the proposed prediction frameworks is able to predict treatment outcomes in epilepsy with similar accuracy as compared with "expert-based" clinical decision, or is able to predict naming impairment outcomes that are very similar to real outcomes as observed on standard language tests.
| Original language | English |
|---|---|
| Title of host publication | Machine Learning and Medical Imaging |
| Publisher | Elsevier Inc. |
| Pages | 455-476 |
| Number of pages | 22 |
| ISBN (Electronic) | 9780128041147 |
| ISBN (Print) | 9780128040768 |
| DOIs | |
| Publication status | Published - 2016 Aug 9 |
| Externally published | Yes |
Fingerprint
Keywords
- Computational modeling
- Diffusion tensor imaging (DTI)
- Machine learning
- Naming impairment prediction
- Structural brain connectome
- Temporal lobe epilepsy (TLE)
- Treatment outcome prediction
ASJC Scopus subject areas
- Engineering(all)
Cite this
Neuronal network architecture and temporal lobe epilepsy : A connectome-based and machine learning study. / Munsell, B. C.; Wu, Guorong; Keller, S.; Fridriksson, J.; Weber, B.; Styner, M.; Shen, Dinggang; Bonilha, L.
Machine Learning and Medical Imaging. Elsevier Inc., 2016. p. 455-476.Research output: Chapter in Book/Report/Conference proceeding › Chapter
}
TY - CHAP
T1 - Neuronal network architecture and temporal lobe epilepsy
T2 - A connectome-based and machine learning study
AU - Munsell, B. C.
AU - Wu, Guorong
AU - Keller, S.
AU - Fridriksson, J.
AU - Weber, B.
AU - Styner, M.
AU - Shen, Dinggang
AU - Bonilha, L.
PY - 2016/8/9
Y1 - 2016/8/9
N2 - This chapter provides an overview of two different clinical studies that apply machine learning techniques that create computational models capable of identifying abnormal network connections in the structural brain connectomes of patients with temporal lobe epilepsy (TLE). In particular, using only the structural connectome we introduce two new computational approaches aimed at predicting: (1) the surgical treatment outcome of patients with TLE, and (2) the naming impairment performance of patients with TLE. In both studies, prediction frameworks are trained to identify abnormal network connection patterns (ie, biomarkers) by applying supervised learning techniques to brain network features based on edge or node graph measures derived exclusively from the structural connectome. Furthermore, the performance of the proposed prediction frameworks is able to predict treatment outcomes in epilepsy with similar accuracy as compared with "expert-based" clinical decision, or is able to predict naming impairment outcomes that are very similar to real outcomes as observed on standard language tests.
AB - This chapter provides an overview of two different clinical studies that apply machine learning techniques that create computational models capable of identifying abnormal network connections in the structural brain connectomes of patients with temporal lobe epilepsy (TLE). In particular, using only the structural connectome we introduce two new computational approaches aimed at predicting: (1) the surgical treatment outcome of patients with TLE, and (2) the naming impairment performance of patients with TLE. In both studies, prediction frameworks are trained to identify abnormal network connection patterns (ie, biomarkers) by applying supervised learning techniques to brain network features based on edge or node graph measures derived exclusively from the structural connectome. Furthermore, the performance of the proposed prediction frameworks is able to predict treatment outcomes in epilepsy with similar accuracy as compared with "expert-based" clinical decision, or is able to predict naming impairment outcomes that are very similar to real outcomes as observed on standard language tests.
KW - Computational modeling
KW - Diffusion tensor imaging (DTI)
KW - Machine learning
KW - Naming impairment prediction
KW - Structural brain connectome
KW - Temporal lobe epilepsy (TLE)
KW - Treatment outcome prediction
UR - http://www.scopus.com/inward/record.url?scp=85017465505&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85017465505&partnerID=8YFLogxK
U2 - 10.1016/B978-0-12-804076-8.00016-5
DO - 10.1016/B978-0-12-804076-8.00016-5
M3 - Chapter
AN - SCOPUS:85017465505
SN - 9780128040768
SP - 455
EP - 476
BT - Machine Learning and Medical Imaging
PB - Elsevier Inc.
ER -